Embodiments of the present disclosure relate to a method and an apparatus for alerting threats to users. The apparatus may capture a plurality of signals including at least one of Electro-Magnetic (E-M) signals and sound signals. The E-M signal and sound signals are used to detect objects around the user. A threat to the user is predicted based on the objects around the user and one or more alerts are generated such that the user avoids the threat. The prediction of the threat enables the user to take an action even before the threat has occurred. Also, the alerts are generated based on the prediction such that the user can avoid the threat well in advance of the occurrence of the threat.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
2. The method as claimed in claim 1, wherein the plurality of signals are time series data.
This invention relates to processing time series data, which is a sequence of data points collected over time. The challenge addressed is efficiently analyzing and extracting meaningful patterns from such data, which is common in fields like finance, healthcare, and industrial monitoring. The method involves receiving a plurality of signals, where each signal represents time series data. The signals are processed to identify and extract relevant features or patterns, enabling improved decision-making or predictive modeling. The method may include steps such as filtering, normalization, or transformation of the time series data to enhance the accuracy of the analysis. Additionally, the method may involve applying machine learning techniques to the processed data to detect anomalies, trends, or other significant events. The invention aims to provide a robust and scalable approach to handling time series data, ensuring reliable and efficient analysis in real-world applications.
3. The method as claimed in claim 1, further comprises classifying the one or more objects into one or more categories using a CNN classifier.
This invention relates to object detection and classification in digital images or video frames. The problem addressed is the need for efficient and accurate identification and categorization of objects within visual data, which is critical for applications such as autonomous navigation, surveillance, and augmented reality. The method involves processing an input image or video frame to detect one or more objects. A convolutional neural network (CNN) classifier is then applied to analyze the detected objects and categorize them into predefined categories. The CNN classifier is trained to recognize distinct features of objects and assign them to appropriate classes based on learned patterns. This classification step enhances the system's ability to distinguish between different types of objects, improving decision-making in downstream applications. The method may also include preprocessing the input image to enhance object detection accuracy, such as noise reduction or contrast adjustment. The detected objects are then passed through the CNN classifier, which outputs the classified categories. This approach ensures that objects are not only identified but also accurately labeled, enabling more precise and context-aware processing in automated systems. The use of a CNN classifier leverages deep learning techniques to achieve high classification accuracy, making the method suitable for real-time applications where rapid and reliable object recognition is essential.
7. The method as claimed in claim 1, wherein the one or more alerts are generated further based on a severity of the threat, wherein the severity of the threat is determined based on the one or more categories of the one or more objects and an estimated impact caused by the one or more objects to the user based on the variation in the relative position of the user with respect to the one or more objects.
This invention relates to threat detection and alert systems, specifically for assessing and prioritizing threats based on severity. The system identifies objects in a user's environment, categorizes them, and monitors their relative positions to the user. When an object is detected as a potential threat, the system generates alerts based on the object's category and the estimated impact of its movement or position change on the user. The severity of the threat is determined by analyzing the object's category and the degree of positional variation relative to the user. For example, a fast-moving object in a high-risk category may trigger a higher-severity alert than a stationary or slow-moving object in a lower-risk category. The system dynamically adjusts alert prioritization to ensure timely and relevant threat notifications. This approach enhances situational awareness by focusing on the most critical threats, reducing alert fatigue, and improving user safety in environments where multiple objects may pose varying levels of risk. The method integrates object detection, categorization, positional tracking, and impact assessment to provide a comprehensive threat evaluation framework.
9. The mobile phone as claimed in claim 8, wherein the processor receives the plurality of signals as time series data.
A mobile phone system is designed to process and analyze signals received from various sources, particularly in applications such as health monitoring, environmental sensing, or industrial diagnostics. The system addresses the challenge of efficiently handling and interpreting complex signal data, which often arrives as time-series information. The mobile phone includes a processor configured to receive and process multiple signals as time-series data, allowing for real-time or near-real-time analysis. The processor may apply algorithms to detect patterns, anomalies, or trends within the time-series data, enabling applications such as continuous health monitoring, predictive maintenance, or environmental tracking. The system may also include additional components, such as sensors or communication interfaces, to collect and transmit the signals to the processor. By processing signals as time-series data, the mobile phone can provide more accurate and context-aware insights compared to traditional methods that rely on static or infrequent measurements. This approach enhances the device's capability to support dynamic and data-driven decision-making in various fields.
10. The mobile phone as claimed in claim 8, wherein the processor is further configured to classify the one or more objects into one or more categories using a CNN classifier.
A mobile phone includes a camera for capturing images or video and a processor for analyzing the captured visual data. The processor is configured to detect one or more objects within the captured visual data using a convolutional neural network (CNN) object detection model. The detected objects are then classified into one or more predefined categories using a CNN classifier. The CNN classifier processes the visual features extracted by the object detection model to assign each detected object to a specific category. This classification allows the mobile phone to identify and categorize objects in real-time, enabling applications such as augmented reality, image search, or automated content tagging. The system leverages deep learning techniques to improve accuracy and efficiency in object recognition and classification tasks. The mobile phone may further include a display for presenting the classified objects or a communication module for transmitting the classification results to an external device. The CNN classifier is trained on a dataset of labeled images to ensure accurate categorization of objects into the predefined categories.
14. The mobile phone as claimed in claim 8, wherein the processor generates the one or more alerts further based on a severity of the threat, wherein the severity of the threat is determined based on the one or more categories of the one or more objects and an estimated impact caused by the one or more objects to the user based on the variation in the relative position of the user with respect to the one or more objects.
A mobile phone system monitors a user's environment to detect potential threats by analyzing objects in the vicinity using sensors such as cameras or radar. The system categorizes detected objects and assesses their threat level based on their type and the user's relative position. For example, a moving vehicle approaching the user may be classified as a higher threat than a stationary object. The system calculates the severity of the threat by evaluating the object's category and the potential impact on the user, considering factors like proximity, speed, and direction. Based on this analysis, the phone generates alerts to warn the user, with the alert type and urgency adjusted according to the threat's severity. For instance, a high-severity threat may trigger an immediate audible alert, while a lower-severity threat may result in a vibration or visual notification. The system continuously updates threat assessments as the user's position changes relative to surrounding objects, ensuring timely and relevant warnings. This approach enhances situational awareness and safety by dynamically adapting to environmental risks.
15. The mobile phone as claimed in claim 8, further comprises a user interface to provide the one or more alerts to the user.
A mobile phone system is designed to enhance user awareness of environmental conditions, particularly in scenarios where visibility is impaired, such as during nighttime or adverse weather. The device includes a sensor system that detects environmental factors like light levels, temperature, humidity, or air quality. Based on the sensor data, the phone generates alerts to inform the user of potential hazards or changes in conditions. These alerts may be visual, auditory, or haptic, depending on the user's preferences and the severity of the detected conditions. The user interface allows customization of alert types and thresholds, ensuring the system adapts to individual needs. Additionally, the phone may integrate with external sensors or networks to provide broader environmental monitoring. The goal is to improve situational awareness and safety by proactively notifying users of environmental changes that could impact their activities or well-being. The system may also log historical data for trend analysis or share alerts with other devices in a networked environment.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
August 10, 2020
June 4, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.